深度学习在和弦识别中表现不佳，研究发现稀有和弦是难点。
Chord Recognition with Deep Learning
- 通过生成模型测试假设，发现罕见和弦识别率低
- 音高增强使识别准确率显著提升
- 结合节拍检测提升模型可解释性，适合音频分析研究者
自深度学习兴起以来，自动和弦识别进展缓慢。为探究原因，本文对现有方法进行实验，并利用生成模型的最新进展验证假设。结果表明，和弦分类器在稀有和弦上表现较差，而音高数据增强能有效提升准确率。从生成模型中提取的特征并未带来帮助，但合成数据展现出巨大潜力。最后，通过引入节拍检测提升了模型输出的可解释性，取得了领域内部分最佳结果，并提供定性分析。尽管仍有许多工作待完成，本文希望为后续研究提供可行路径。
原文摘要 · Abstract (English)
Progress in automatic chord recognition has been slow since the advent of deep learning in the field. To understand why, I conduct experiments on existing methods and test hypotheses enabled by recent developments in generative models. Findings show that chord classifiers perform poorly on rare chords and that pitch augmentation boosts accuracy. Features extracted from generative models do not help and synthetic data presents an exciting avenue for future work. I conclude by improving the interpretability of model outputs with beat detection, reporting some of the best results in the field and providing qualitative analysis. Much work remains to solve automatic chord recognition, but I hope this thesis will chart a path for others to try.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。